NotesFAQContact Us
Search Tips
ERIC Number: ED090248
Record Type: Non-Journal
Publication Date: 1974-Apr
Pages: 9
Abstractor: N/A
Reference Count: N/A
ANCOVA Procedures in Time-Series Experiments: An Illustrative Example.
Willson, Victor L.
A statistical model for analysis of multiple time-series observation is briefly outlined. The model incorporates a change parameter corresponding to intervention or interruption of the dependent series. The additional time-series are included in the model as covariates. The practical application of the procedure is illustrated with traffic fatality data from several Northeast states. The intervention variable is a legislative crackdown on speeding offenders in Connecticut, which was claimed to have produced a significant drop in the traffic fatality rate. The analysis using neighboring states as covariates results in a change to nonsignificance for the intervention effect. The seasonal nature of the data also illustrates the applicability of the procedure when seasonality is present, so that no season adjustments are required. (Author)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A